I built a mmWave material classification radar (2025)(gauthier-lechevalier.com) |
I built a mmWave material classification radar (2025)(gauthier-lechevalier.com) |
Asbestos doesn't work like that. If you don't touch it, you're fine. You can live your whole life in asbestos building and be safe. You may even be worse off if you decide to get rid of it and start tearing down walls.
So it's good that it's banned, but if there's no reason to touch it, you're just making a tinfoil hat. There's more harm from the fear of it.
Isnt mmWave pretty similar (in theory) to short-ish range wireless directional antennas? What people used to call point to point "microwave" transmission?
Crazy idea but could your mmWave radar hardware also be (not simultanouslyl) used to transmit data? No idea what a Rotman Lens is but I would imagine that maybe it could be useful for transmission as well.
This needs to join the families of devices that find wooden studs, electrical wiring, and plumbing. This is a general purpose technology. It can be reprogrammed to find other things. It should be in a blister-pack at Home Depot if it can be made cheaply, and in a hard case at Tool Town if it can't.
In the end the most reliable way of locating studs I found was going outside, measuring the distance between the nails in the exterior cladding, and then using those measurements on the corresponding inside wall.
Any company dealing with construction waste disposal will want one.
Both will have no problem shelling out 1000 euro per unit.
If you'd like to learn more about the module:
https://www.ti.com/tool/IWRL6432BOOST
Edit: maybe I am seeing AI everywhere! False positive. :-)
Unless I missed something, it seems the "POC" device still made no effort to address this, which is the core feature — it just demonstrated classifying some other common materials. If that's true then the conclusions make no sense to me - why would customers be lining up if you still haven't proven the actual concept?
(Of course, the place I've dealt with this the most was a former post office building from the late 1930s - we didn't really need tests, a historian would probably have just said "of course you have asbestos" :-) It does expose an interesting problem with the labeling part, though: USPS as an ancient federal agency has its own rules for things and had a distinct asbestos markers - an A in a point-down triangle - which we fortunately found documentation for, it isn't public record.)
I'm sure this can be annoying when people do this, but I can't help myself lol. I wonder if you could operate in a different modality and find discontinuities in material properties rather than use it as a classifier. For some reason skin cancer detection popped into my head, but general purpose inspection/detection cases for any discontinuities might be pretty helpful. Depending on the resolution/size of the field it's inspecting a realtime camera overlay might be interesting for correlation sake.
Does it also work through other materials. i.e. through a drywall etc.
very cool project
Like if you trained a machine learning algorithm to differentiate 10 samples of asbestos containing material from 10 non-asbestos containing materials I wouldn't believe it would work with all the many kinds of materials you would find out in the field in all the configurations that are out there.
All that talk of how the electromagnetic properties of asbestos-containing materials are different are pretty handwavy and lack a theoretical explanation of where the dividing line between different materials ought to be. Overall it strikes me as the kind of half-baked idea that people suddenly feel empowered to do thanks to AI.
About AI. Two things you learn in school : for centuries, we measured the world and modelled it using differential equations, and other mathematical concepts. Humans just have a certain limit to finding patterns, and this limit is covered by AI, which when you come to think of it is just a series of calculations to model statistical phenomenons.
Physics is a statistical phenomenon, therefore AI is now being used everywhere in physics to model the world.
The guy is scrappy.
I've been down the mmWave rabbit hole for the last 6 months, making sensors to put around the house to control automations for lights and so forth. They're pretty great.
For my use case the advantage over PIR is they do presence detection, so no more lights shutting off when you're sitting on the toilet.
Pretty amazing you can pick up basic mmWave sensors for a few bucks on amazon, and mate them to an esp32 board which is another couple bucks. It's so much fun as a hobby!
(VCU128s are relatively large, HBM equipped FPGAs for people not aware)